From: Gao Xiang <gaoxiang25@huawei.com>
To: <chao@kernel.org>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
<devel@driverdev.osuosl.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
<linux-fsdevel@vger.kernel.org>, <linux-erofs@lists.ozlabs.org>,
Miao Xie <miaoxie@huawei.com>, <weidu.du@huawei.com>,
Fang Wei <fangwei1@huawei.com>, Gao Xiang <gaoxiang25@huawei.com>
Subject: [RFC PATCH 0/8] staging: erofs: decompression inplace approach
Date: Sat, 15 Jun 2019 02:16:11 +0800 [thread overview]
Message-ID: <20190614181619.64905-1-gaoxiang25@huawei.com> (raw)
Hi,
After working on for more than half a year, the detail of erofs decompression
inplace is almost determined and ready for linux-next.
Currently, inplace IO is used if the whole compressed data is used
in order to reduce compressed pages extra memory overhead and an extra
memcpy (the only one memcpy) will be used for each inplace IO since
temporary buffer is needed to keep decompressing safe for inplace IO.
However, most of lz-based decompression algorithms support decompression
inplace by their algorithm designs, such as LZ4, LZO, etc.
If iend - oend margin is large enough, decompression inplace can be done
in the same buffer safely, as illustrated below:
start of compressed logical extent
| end of this logical extent
| |
______v___________________________v________
... | page 6 | page 7 | page 8 | page 9 | ...
|__________|__________|__________|__________|
. ^ . ^
. |compressed|
. | data |
. . .
|< dstsize >|<margin>|
oend iend
op ip
Fixed-size output compression can make the full use of this feature
to reduce memory overhead and avoid extra memcpy compared with fixed-size
input compression since iend is strictly not less than oend for fixed-size
output compression with inplace IO to last pages.
In addition, erofs compression indexes have been improved as well by
introducing compacted compression indexes.
These two techniques all benefit sequential read (on x86_64, 710.8MiB/s
-> 755.4MiB/s; on Kirin980, 725MiB/s -> 812MiB/s) therefore erofs
could have similar sequential read performance against ext4 in a larger
CR range on high-spend SSD / NVMe devices as well.
However, note that it is _cpu vs storage device_ balance, there is no
absolute performance conclusion for all on-market combinations.
At last, this is RFC patch v1, which means it is not suitable for
merging soon... I'm still working on it, testing its stability
these days and hope these patches get merged for 5.3 LTS
(if 5.3 is a LTS version).
The series is based on staging-next with the following patches, which
can be merged in advance:
[PATCH v3 1/2] staging: erofs: add requirements field in superblock
[PATCH v2 2/2] staging: erofs: rename data_mapping_mode to datamode
Test images:
name size CR
enwik9 1000000000 1.00
enwik9_4k.squashfs.img 621211648 1.61
enwik9_4k.erofs.img 558133248 1.79
enwik9_8k.squashfs.img 556191744 1.80
enwik9_16k.squashfs.img 502661120 1.99
enwik9_128k.squashfs.img 398204928 2.51
Test Environment:
CPU: Intel(R) Core(TM) i5-8250U CPU @ 1.60GHz (4 cores, 8 threads)
DDR: 8G
SSD: INTEL SSDPEKKF360G7H
Kernel: Linux 5.2-rc3+ (with lz4-1.8.3 algorithm)
Test configuration:
squashfs:
CONFIG_SQUASHFS=y
CONFIG_SQUASHFS_FILE_DIRECT=y
CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU=y
CONFIG_SQUASHFS_LZ4=y
CONFIG_SQUASHFS_4K_DEVBLK_SIZE=y
erofs:
CONFIG_EROFS_FS_USE_VM_MAP_RAM=y
CONFIG_EROFS_FS_ZIP=y
CONFIG_EROFS_FS_CLUSTER_PAGE_LIMIT=1
CONFIG_EROFS_FS_ZIP_CACHE_BIPOLAR=y
with intel_pstate=disable,
8 cpus on at 1801000 scaling_{min,max}_freq,
userspace scaling_governor
Sequential read results (MiB/s):
1 2 3 4 5 avg
enwik9_4k.ext4.img 767 770 738 726 724 745
enwik9_4k.erofs.img 756 745 770 746 760 755.4
enwik9_4k.squashfs.img 90.3 83.0 94.3 90.7 92.6 90.18
enwik9_8k.squashfs.img 111 108 110 108 110 109.4
enwik9_16k.squashfs.img 158 163 146 165 174 161.2
enwik9_128k.squashfs.img 324 314 262 262 296 291.6
Thanks,
Gao Xiang
Gao Xiang (8):
staging: erofs: add compacted ondisk compression indexes
staging: erofs: add compacted compression indexes support
staging: erofs: move per-CPU buffers implementation to utils.c
staging: erofs: move stagingpage operations to compress.h
staging: erofs: introduce generic decompression backend
staging: erofs: introduce LZ4 decompression inplace
staging: erofs: switch to new decompression backend
staging: erofs: integrate decompression inplace
drivers/staging/erofs/Makefile | 2 +-
drivers/staging/erofs/compress.h | 62 ++++
drivers/staging/erofs/data.c | 4 +-
drivers/staging/erofs/decompressor.c | 321 ++++++++++++++++++
drivers/staging/erofs/erofs_fs.h | 60 +++-
drivers/staging/erofs/inode.c | 12 +-
drivers/staging/erofs/internal.h | 58 +++-
drivers/staging/erofs/unzip_vle.c | 368 ++------------------
drivers/staging/erofs/unzip_vle.h | 38 +--
drivers/staging/erofs/unzip_vle_lz4.c | 229 -------------
drivers/staging/erofs/utils.c | 12 +
drivers/staging/erofs/zmap.c | 462 ++++++++++++++++++++++++++
12 files changed, 996 insertions(+), 632 deletions(-)
create mode 100644 drivers/staging/erofs/compress.h
create mode 100644 drivers/staging/erofs/decompressor.c
delete mode 100644 drivers/staging/erofs/unzip_vle_lz4.c
create mode 100644 drivers/staging/erofs/zmap.c
--
2.17.1
next reply other threads:[~2019-06-14 18:17 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-14 18:16 Gao Xiang [this message]
2019-06-14 18:16 ` [RFC PATCH 1/8] staging: erofs: add compacted ondisk compression indexes Gao Xiang
2019-06-14 18:16 ` [RFC PATCH 2/8] staging: erofs: add compacted compression indexes support Gao Xiang
2019-06-14 18:16 ` [RFC PATCH 3/8] staging: erofs: move per-CPU buffers implementation to utils.c Gao Xiang
2019-06-14 18:16 ` [RFC PATCH 4/8] staging: erofs: move stagingpage operations to compress.h Gao Xiang
2019-06-14 18:16 ` [RFC PATCH 5/8] staging: erofs: introduce generic decompression backend Gao Xiang
2019-06-14 18:16 ` [RFC PATCH 6/8] staging: erofs: introduce LZ4 decompression inplace Gao Xiang
2019-06-14 18:16 ` [RFC PATCH 7/8] staging: erofs: switch to new decompression backend Gao Xiang
2019-06-14 18:16 ` [RFC PATCH 8/8] staging: erofs: integrate decompression inplace Gao Xiang
2019-06-17 20:36 ` [RFC PATCH 0/8] staging: erofs: decompression inplace approach Greg Kroah-Hartman
2019-06-18 1:47 ` Gao Xiang
2019-06-18 5:47 ` Greg Kroah-Hartman
2019-06-18 6:18 ` Gao Xiang
2019-06-18 6:45 ` Greg Kroah-Hartman
2019-06-18 6:52 ` Gao Xiang
2019-06-18 7:05 ` Greg Kroah-Hartman
2019-06-18 7:13 ` Gao Xiang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190614181619.64905-1-gaoxiang25@huawei.com \
--to=gaoxiang25@huawei.com \
--cc=chao@kernel.org \
--cc=devel@driverdev.osuosl.org \
--cc=fangwei1@huawei.com \
--cc=gregkh@linuxfoundation.org \
--cc=linux-erofs@lists.ozlabs.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=miaoxie@huawei.com \
--cc=weidu.du@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).